
# ini merupakan cell untuk code
print("dan ini adalah cell code tempat menuliskan code python")

dan ini adalah cell code tempat menuliskan code python


angka = 10
angka

10


angka

10


dss_name = "Data Science Series: Streamlining Invoice Processing"
print(dss_name)

Data Science Series: Streamlining Invoice Processing


## code here
dss_name == dss_name

True


# True = 11


# cek daftar keyword
import keyword
keyword.kwlist

['False',
 'None',
 'True',
 'and',
 'as',
 'assert',
 'async',
 'await',
 'break',
 'class',
 'continue',
 'def',
 'del',
 'elif',
 'else',
 'except',
 'finally',
 'for',
 'from',
 'global',
 'if',
 'import',
 'in',
 'is',
 'lambda',
 'nonlocal',
 'not',
 'or',
 'pass',
 'raise',
 'return',
 'try',
 'while',
 'with',
 'yield']


dss_name

'Data Science Series: Streamlining Invoice Processing'


# code here
type(dss_name)

str


nilai_ta = 100.0
nilai_fiqey = 90.0


type(nilai_ta)

float


# code here
nilai_ta - nilai_fiqey

10.0


2 + 2 == 5
# == --> untuk mengecek kondisi (apakah sama?)

False


# list berikut mengandung informasi nama, kota domisili, umur, apakah sudah menikah?
data_list = ['Sari', 'Jakarta', 27, False]
# 0, 1, 2, 3


# cek tipe data my_list
type(data_list)

list


# akses umur sari
data_list[2]

27


# akses informasi kota domilisi dari seorang Sari, dimana informasi kota domilisi terletak di urutan ke-2 (index ke-1)
data_list[1]

'Jakarta'


# coba kita tambahkan informasi pekerjaan 'Sari', yaitu 'Data Scientist'
data_list.append('Data Scientist')
data_list

['Sari', 'Jakarta', 27, False, 'Data Scientist']


# dictionary berisi informasi tentang seseorang
data_dict = {
    'nama': 'Sari',
    'kota_domisili': 'Jakarta',
    'umur': 27,
    'menikah': False
}


# code here
type(data_dict)

dict


# code here
data_dict['kota_domisili']

'Jakarta'

if kondisi:
    # Kode yang akan dieksekusi jika kondisi benar
else:
    # Kode yang akan dieksekusi jika kondisi salah


angka = -10

# Penggunaan if-else untuk menentukan apakah angka positif, negatif, atau nol
if angka > 0:
    print("Angka ini adalah positif.")
elif angka < 0: # else -if
    print("Angka ini adalah negatif.")
else:
    print("Angka ini adalah nol.")

Angka ini adalah negatif.

def nama_fungsi(parameter):
    perintah


# fungsi luas_segitiga
def luas_persegi(sisi): # parameter : sesuatu yang bisa kita ubah dg mendefinisikannya saat pemanggilan fungsi
    hasil = sisi * sisi
    return hasil # mengembalikan hasil proses dari suatu fungsi


# memanggil fungsi
result2 = luas_persegi(sisi = 4)
# result


luas_persegi(sisi=5)

25


jabodetabek = ['Jakarta', 'Bogor', 'Depok', 'Tangerang', 'Bekasi']

# for loop
for kota in jabodetabek: # x: perwakilan nama sebuah elemen dari jabodetabek
  print("kota: ",kota)
  print("----")

kota:  Jakarta
----
kota:  Bogor
----
kota:  Depok
----
kota:  Tangerang
----
kota:  Bekasi
----


import pandas as pd # aliasing
print(pd.__version__)

2.1.4

pandas.read_csv("path/data")


receipts = pd.read_csv('data_input/receipt_cleaned.csv')
receipts


# code here
receipts.head()


# cek tipe data
receipts.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 36 entries, 0 to 35
Data columns (total 5 columns):
 #   Column       Non-Null Count  Dtype  
---  ------       --------------  -----  
 0   receipt_id   36 non-null     object 
 1   item_name    36 non-null     object 
 2   count        36 non-null     float64
 3   price        36 non-null     int64  
 4   total_price  36 non-null     int64  
dtypes: float64(1), int64(2), object(2)
memory usage: 1.5+ KB

df['column_name'] = df['column_name'].astype('new_data_types')


receipts['item_name'].nunique()

34


# change & check data type
receipts['item_name'].astype('category')

0                     real ganache
1                         egg tart
2                      pizza toast
3                kopi susu kolonel
4                       s-ovaltine
5             m-carame 1 black tea
6                      bbq chicken
7                       le mineral
8             potato sausage bread
9            oreo green tea spread
10       white choco banana spread
11                     choco devil
12                cp 360 club card
13                      talam ungu
14                      mika kecil
15              tahu ikan oma giok
16                           serbu
17              choco peanut bread
18    se'i sapi sambal matah ( r )
19        se'i s-pi lada hitam (j)
20                      nasi putih
21               milk shake coklat
22                    es kopi susu
23                  mineral 600 ml
24                  bulgogi rice r
25                       arem arem
26                          kroket
27                       arem arem
28                 pepenero pastel
29                              tt
30                   lemonade 16oz
31                beef c roll 3pcs
32                       kaya bred
33       futami 17 green tea (clas
34                        egg tart
35           grain croque monsieur
Name: item_name, dtype: category
Categories (34, object): ['arem arem', 'bbq chicken', 'beef c roll 3pcs', 'bulgogi rice r', ..., 'tahu ikan oma giok', 'talam ungu', 'tt', 'white choco banana spread']


receipts['item_name'].info()

<class 'pandas.core.series.Series'>
RangeIndex: 36 entries, 0 to 35
Series name: item_name
Non-Null Count  Dtype 
--------------  ----- 
36 non-null     object
dtypes: object(1)
memory usage: 416.0+ bytes


receipts['item_name'].str.lower()

0                     real ganache
1                         egg tart
2                      pizza toast
3                kopi susu kolonel
4                       s-ovaltine
5             m-carame 1 black tea
6                      bbq chicken
7                       le mineral
8             potato sausage bread
9            oreo green tea spread
10       white choco banana spread
11                     choco devil
12                cp 360 club card
13                      talam ungu
14                      mika kecil
15              tahu ikan oma giok
16                           serbu
17              choco peanut bread
18    se'i sapi sambal matah ( r )
19        se'i s-pi lada hitam (j)
20                      nasi putih
21               milk shake coklat
22                    es kopi susu
23                  mineral 600 ml
24                  bulgogi rice r
25                       arem arem
26                          kroket
27                       arem arem
28                 pepenero pastel
29                              tt
30                   lemonade 16oz
31                beef c roll 3pcs
32                       kaya bred
33       futami 17 green tea (clas
34                        egg tart
35           grain croque monsieur
Name: item_name, dtype: object


# mengubah semua teks dalam kolom 'item_name' menjadi huruf kecil
receipts['item_name'].str.lower()[5]

'm-carame 1 black tea'


# mengubah semua teks dalam kolom 'receipt_id' menjadi huruf besar
# pak muslim & pak anthony
receipts['receipt_id'] = receipts['receipt_id'].str.upper()
receipts['receipt_id']

0     ID0000
1     ID0000
2     ID0000
3     ID0001
4     ID0002
5     ID0003
6     ID0004
7     ID0005
8     ID0006
9     ID0006
10    ID0006
11    ID0007
12    ID0007
13    ID0008
14    ID0008
15    ID0009
16    ID0010
17    ID0010
18    ID0011
19    ID0011
20    ID0011
21    ID0011
22    ID0012
23    ID0013
24    ID0013
25    ID0014
26    ID0014
27    ID0015
28    ID0015
29    ID0016
30    ID0017
31    ID0018
32    ID0018
33    ID0019
34    ID0019
35    ID0019
Name: receipt_id, dtype: object


# contoh menghapus '()' dalam string
receipts['item_name'].str.replace('(', '').str.replace(')', '')

0                   real ganache
1                       egg tart
2                    pizza toast
3              kopi susu kolonel
4                     s-ovaltine
5           m-carame 1 black tea
6                    bbq chicken
7                     le mineral
8           potato sausage bread
9          oreo green tea spread
10     white choco banana spread
11                   choco devil
12              cp 360 club card
13                    talam ungu
14                    mika kecil
15            tahu ikan oma giok
16                         serbu
17            choco peanut bread
18    se'i sapi sambal matah  r 
19        se'i s-pi lada hitam j
20                    nasi putih
21             milk shake coklat
22                  es kopi susu
23                mineral 600 ml
24                bulgogi rice r
25                     arem arem
26                        kroket
27                     arem arem
28               pepenero pastel
29                            tt
30                 lemonade 16oz
31              beef c roll 3pcs
32                     kaya bred
33      futami 17 green tea clas
34                      egg tart
35         grain croque monsieur
Name: item_name, dtype: object


# mengganti '-' dengan ' ' (spasi) dalam kolom 'item_name'
receipts['item_name'].str.replace('-', ' ')

0                     real ganache
1                         egg tart
2                      pizza toast
3                kopi susu kolonel
4                       s ovaltine
5             m carame 1 black tea
6                      bbq chicken
7                       le mineral
8             potato sausage bread
9            oreo green tea spread
10       white choco banana spread
11                     choco devil
12                cp 360 club card
13                      talam ungu
14                      mika kecil
15              tahu ikan oma giok
16                           serbu
17              choco peanut bread
18    se'i sapi sambal matah ( r )
19        se'i s pi lada hitam (j)
20                      nasi putih
21               milk shake coklat
22                    es kopi susu
23                  mineral 600 ml
24                  bulgogi rice r
25                       arem arem
26                          kroket
27                       arem arem
28                 pepenero pastel
29                              tt
30                   lemonade 16oz
31                beef c roll 3pcs
32                       kaya bred
33       futami 17 green tea (clas
34                        egg tart
35           grain croque monsieur
Name: item_name, dtype: object


# code here
receipts['receipt_id'].value_counts()

receipt_id
ID0011    4
ID0000    3
ID0006    3
ID0019    3
ID0007    2
ID0008    2
ID0013    2
ID0014    2
ID0015    2
ID0018    2
ID0010    2
ID0004    1
ID0005    1
ID0003    1
ID0009    1
ID0001    1
ID0002    1
ID0012    1
ID0016    1
ID0017    1
Name: count, dtype: int64


# code here (pak heinz)
receipts["item_name"].value_counts(ascending=False)

item_name
arem arem                       2
egg tart                        2
real ganache                    1
se'i s-pi lada hitam (j)        1
nasi putih                      1
milk shake coklat               1
es kopi susu                    1
mineral 600 ml                  1
bulgogi rice r                  1
kroket                          1
pepenero pastel                 1
tt                              1
lemonade 16oz                   1
beef c roll 3pcs                1
kaya bred                       1
futami 17 green tea (clas       1
se'i sapi sambal matah ( r )    1
choco peanut bread              1
serbu                           1
tahu ikan oma giok              1
mika kecil                      1
talam ungu                      1
cp 360 club card                1
choco devil                     1
white choco banana spread       1
oreo green tea spread           1
potato sausage bread            1
le mineral                      1
bbq chicken                     1
m-carame 1 black tea            1
s-ovaltine                      1
kopi susu kolonel               1
pizza toast                     1
grain croque monsieur           1
Name: count, dtype: int64


receipts[receipts['item_name'] == 'arem arem']


# code here: pak husada
receipts[receipts['receipt_id'] == 'ID0015']


# code here: pak heinz
receipt_above50k = receipts[receipts['total_price'] > 50000]
receipt_above50k


# optional: mengambil yang unique saja
receipt_above50k['receipt_id'].unique()

array(['ID0006', 'ID0007', 'ID0010', 'ID0011', 'ID0012', 'ID0015'],
      dtype=object)


import re # untuk cleaning menggunakan regex (regular expression)
import os # untuk pembacaan data image -> baca nama file
import torch

from PIL import Image # untuk membaca gambar
from transformers import DonutProcessor, VisionEncoderDecoderModel


processor = DonutProcessor.from_pretrained("naver-clova-ix/donut-base-finetuned-cord-v2")
model = VisionEncoderDecoderModel.from_pretrained("naver-clova-ix/donut-base-finetuned-cord-v2")

Could not find image processor class in the image processor config or the model config. Loading based on pattern matching with the model's feature extractor configuration.


# set model device
device = "cuda" if torch.cuda.is_available() else "cpu"
model.to(device)

VisionEncoderDecoderModel(
  (encoder): DonutSwinModel(
    (embeddings): DonutSwinEmbeddings(
      (patch_embeddings): DonutSwinPatchEmbeddings(
        (projection): Conv2d(3, 128, kernel_size=(4, 4), stride=(4, 4))
      )
      (norm): LayerNorm((128,), eps=1e-05, elementwise_affine=True)
      (dropout): Dropout(p=0.0, inplace=False)
    )
    (encoder): DonutSwinEncoder(
      (layers): ModuleList(
        (0): DonutSwinStage(
          (blocks): ModuleList(
            (0-1): 2 x DonutSwinLayer(
              (layernorm_before): LayerNorm((128,), eps=1e-05, elementwise_affine=True)
              (attention): DonutSwinAttention(
                (self): DonutSwinSelfAttention(
                  (query): Linear(in_features=128, out_features=128, bias=True)
                  (key): Linear(in_features=128, out_features=128, bias=True)
                  (value): Linear(in_features=128, out_features=128, bias=True)
                  (dropout): Dropout(p=0.0, inplace=False)
                )
                (output): DonutSwinSelfOutput(
                  (dense): Linear(in_features=128, out_features=128, bias=True)
                  (dropout): Dropout(p=0.0, inplace=False)
                )
              )
              (drop_path): DonutSwinDropPath(p=0.1)
              (layernorm_after): LayerNorm((128,), eps=1e-05, elementwise_affine=True)
              (intermediate): DonutSwinIntermediate(
                (dense): Linear(in_features=128, out_features=512, bias=True)
                (intermediate_act_fn): GELUActivation()
              )
              (output): DonutSwinOutput(
                (dense): Linear(in_features=512, out_features=128, bias=True)
                (dropout): Dropout(p=0.0, inplace=False)
              )
            )
          )
          (downsample): DonutSwinPatchMerging(
            (reduction): Linear(in_features=512, out_features=256, bias=False)
            (norm): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
          )
        )
        (1): DonutSwinStage(
          (blocks): ModuleList(
            (0-1): 2 x DonutSwinLayer(
              (layernorm_before): LayerNorm((256,), eps=1e-05, elementwise_affine=True)
              (attention): DonutSwinAttention(
                (self): DonutSwinSelfAttention(
                  (query): Linear(in_features=256, out_features=256, bias=True)
                  (key): Linear(in_features=256, out_features=256, bias=True)
                  (value): Linear(in_features=256, out_features=256, bias=True)
                  (dropout): Dropout(p=0.0, inplace=False)
                )
                (output): DonutSwinSelfOutput(
                  (dense): Linear(in_features=256, out_features=256, bias=True)
                  (dropout): Dropout(p=0.0, inplace=False)
                )
              )
              (drop_path): DonutSwinDropPath(p=0.1)
              (layernorm_after): LayerNorm((256,), eps=1e-05, elementwise_affine=True)
              (intermediate): DonutSwinIntermediate(
                (dense): Linear(in_features=256, out_features=1024, bias=True)
                (intermediate_act_fn): GELUActivation()
              )
              (output): DonutSwinOutput(
                (dense): Linear(in_features=1024, out_features=256, bias=True)
                (dropout): Dropout(p=0.0, inplace=False)
              )
            )
          )
          (downsample): DonutSwinPatchMerging(
            (reduction): Linear(in_features=1024, out_features=512, bias=False)
            (norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
          )
        )
        (2): DonutSwinStage(
          (blocks): ModuleList(
            (0-13): 14 x DonutSwinLayer(
              (layernorm_before): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
              (attention): DonutSwinAttention(
                (self): DonutSwinSelfAttention(
                  (query): Linear(in_features=512, out_features=512, bias=True)
                  (key): Linear(in_features=512, out_features=512, bias=True)
                  (value): Linear(in_features=512, out_features=512, bias=True)
                  (dropout): Dropout(p=0.0, inplace=False)
                )
                (output): DonutSwinSelfOutput(
                  (dense): Linear(in_features=512, out_features=512, bias=True)
                  (dropout): Dropout(p=0.0, inplace=False)
                )
              )
              (drop_path): DonutSwinDropPath(p=0.1)
              (layernorm_after): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
              (intermediate): DonutSwinIntermediate(
                (dense): Linear(in_features=512, out_features=2048, bias=True)
                (intermediate_act_fn): GELUActivation()
              )
              (output): DonutSwinOutput(
                (dense): Linear(in_features=2048, out_features=512, bias=True)
                (dropout): Dropout(p=0.0, inplace=False)
              )
            )
          )
          (downsample): DonutSwinPatchMerging(
            (reduction): Linear(in_features=2048, out_features=1024, bias=False)
            (norm): LayerNorm((2048,), eps=1e-05, elementwise_affine=True)
          )
        )
        (3): DonutSwinStage(
          (blocks): ModuleList(
            (0-1): 2 x DonutSwinLayer(
              (layernorm_before): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
              (attention): DonutSwinAttention(
                (self): DonutSwinSelfAttention(
                  (query): Linear(in_features=1024, out_features=1024, bias=True)
                  (key): Linear(in_features=1024, out_features=1024, bias=True)
                  (value): Linear(in_features=1024, out_features=1024, bias=True)
                  (dropout): Dropout(p=0.0, inplace=False)
                )
                (output): DonutSwinSelfOutput(
                  (dense): Linear(in_features=1024, out_features=1024, bias=True)
                  (dropout): Dropout(p=0.0, inplace=False)
                )
              )
              (drop_path): DonutSwinDropPath(p=0.1)
              (layernorm_after): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
              (intermediate): DonutSwinIntermediate(
                (dense): Linear(in_features=1024, out_features=4096, bias=True)
                (intermediate_act_fn): GELUActivation()
              )
              (output): DonutSwinOutput(
                (dense): Linear(in_features=4096, out_features=1024, bias=True)
                (dropout): Dropout(p=0.0, inplace=False)
              )
            )
          )
        )
      )
    )
    (pooler): AdaptiveAvgPool1d(output_size=1)
  )
  (decoder): MBartForCausalLM(
    (model): MBartDecoderWrapper(
      (decoder): MBartDecoder(
        (embed_tokens): Embedding(57580, 1024, padding_idx=1)
        (embed_positions): MBartLearnedPositionalEmbedding(770, 1024)
        (layers): ModuleList(
          (0-3): 4 x MBartDecoderLayer(
            (self_attn): MBartAttention(
              (k_proj): Linear(in_features=1024, out_features=1024, bias=True)
              (v_proj): Linear(in_features=1024, out_features=1024, bias=True)
              (q_proj): Linear(in_features=1024, out_features=1024, bias=True)
              (out_proj): Linear(in_features=1024, out_features=1024, bias=True)
            )
            (activation_fn): GELUActivation()
            (self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
            (encoder_attn): MBartAttention(
              (k_proj): Linear(in_features=1024, out_features=1024, bias=True)
              (v_proj): Linear(in_features=1024, out_features=1024, bias=True)
              (q_proj): Linear(in_features=1024, out_features=1024, bias=True)
              (out_proj): Linear(in_features=1024, out_features=1024, bias=True)
            )
            (encoder_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
            (fc1): Linear(in_features=1024, out_features=4096, bias=True)
            (fc2): Linear(in_features=4096, out_features=1024, bias=True)
            (final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
          )
        )
        (layernorm_embedding): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
        (layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
      )
    )
    (lm_head): Linear(in_features=1024, out_features=57580, bias=False)
  )
)


# folder path
dir_path = 'data_input/valid/'

# Membuka file teks untuk dibaca (mode: 'r' untuk read)
with open('nama_file.txt', 'r') as file:
    # Membaca seluruh isi file ke dalam satu string
    content = file.read()
    print(content)


# cara membaca suatu file di python
with open('data_input/valid/ID0000.txt') as file:
    print(file.read())

{'menu': [{'nm': 'REAL GANACHE', 'cnt': '1', 'price': '16,500'}, {'nm': 'EGG TART', 'cnt': '1', 'price': '13,000'}, {'nm': 'PIZZA TOAST', 'cnt': '1', 'price': '16,000'}], 'total': {'total_price': '45,500', 'cashprice': '50,000', 'changeprice': '4,500'}}


# cara menggabungkan string di python
dir_path + 'ID0000.png'

'data_input/valid/ID0000.png'


# cara baca onjek gambar di python
Image.open('data_input/valid/ID0000.png')


img_filenames = [] # list nama file gambar
images = [] # list objek gambar
labels = [] # list label dari gambar

# iterasi direktori -> looping untuk mendapatkan seluruh nama file di `data_input/valid``
for file in os.listdir(dir_path):
    if file.endswith(('.png', '.jpg', '.jpeg')): # jika file tsb berekstensi ('.png', '.jpg', '.jpeg')
        # menyimpan nama gambar ke list
        img_filenames.append(file)
        
        # membuka dan menyimpan objek gambar ke list
        images.append(Image.open(dir_path + file))


    elif file.endswith('.txt'):  # jika file tersebut berekstensi .txt
        # membuka file teks dan membaca isinya, lalu menyimpan ke list
        with open(dir_path + file, 'r') as label_file: 
            labels.append(label_file.read())


# mencetak list nama file gambar
print(img_filenames)

['ID0000.png', 'ID0001.png', 'ID0002.png', 'ID0003.png', 'ID0004.png', 'ID0005.png', 'ID0006.png', 'ID0007.png', 'ID0008.png', 'ID0009.png', 'ID0010.png', 'ID0011.png', 'ID0012.png', 'ID0013.png', 'ID0014.png', 'ID0015.png', 'ID0016.png', 'ID0017.png', 'ID0018.png', 'ID0019.png', 'ID0020.png', 'ID0021.png', 'ID0022.png', 'ID0023.png', 'ID0024.png', 'ID0025.png']


# code here
print(labels[6])
images[6]

{'menu': [{'nm': 'POTATO SAUSAGE BREAD', 'cnt': '1', 'price': '19,000'}, {'nm': 'OREO GREEN TEA SPREAD', 'cnt': '1', 'price': '52,000'}, {'nm': 'WHITE CHOCO BANANA SPREAD', 'cnt': '1', 'price': '52,000'}], 'total': {'total_price': '123,000', 'creditcardprice': '123,000'}}


images[6].size

(864, 1296)


pixel_values = processor(images[6], return_tensors="pt").pixel_values


pixel_values.shape

torch.Size([1, 3, 1280, 960])


task_prompt = "<s_cord-v2>"


outputs = model.generate(
        inputs=pixel_values.to(device), # memasukkan input
        
        max_length=model.decoder.config.max_position_embeddings,

        # parameter penting untuk set bahwa kita mau melakukan task document extraction
        decoder_input_ids=processor.tokenizer(task_prompt, add_special_tokens=False, return_tensors="pt")["input_ids"].to(device),
        
        pad_token_id=processor.tokenizer.pad_token_id, # padding
        eos_token_id=processor.tokenizer.eos_token_id, # end of sentence
        bad_words_ids=[[processor.tokenizer.unk_token_id]], 
        return_dict_in_generate=True,
        use_cache=True,
        
        # modify parameters
        early_stopping=True,
        num_beams=2,
        output_scores=True,
    )


outputs.sequences

tensor([[57579, 57526, 57528, 40769, 44398, 54165, 13663, 56992, 50990, 42990,
         43547,  5909, 57527, 57530,  1314, 57529, 57532, 17888, 56239, 57531,
         57522, 57528, 37040, 49429, 42990, 51290,  4004, 42990,  4008,  5176,
         40099, 39415, 57527, 57530,  1314, 57529, 57532, 20017, 52066, 57531,
         57522, 57528, 46193, 53278, 33938, 36277, 18081, 56701, 42990, 40266,
          5178,  5176, 40099, 39415, 57527, 57530,  1314, 57529, 57532, 20017,
         52066, 57531, 57525, 57544, 57546, 40474, 47108, 57545, 57564, 40474,
         47108, 57563, 57543,     2]])


# code here: check .sequences from the outputs
outputs.sequences

tensor([[57579, 57526, 57528, 40769, 44398, 54165, 13663, 56992, 50990, 42990,
         43547,  5909, 57527, 57530,  1314, 57529, 57532, 17888, 56239, 57531,
         57522, 57528, 37040, 49429, 42990, 51290,  4004, 42990,  4008,  5176,
         40099, 39415, 57527, 57530,  1314, 57529, 57532, 20017, 52066, 57531,
         57522, 57528, 46193, 53278, 33938, 36277, 18081, 56701, 42990, 40266,
          5178,  5176, 40099, 39415, 57527, 57530,  1314, 57529, 57532, 20017,
         52066, 57531, 57525, 57544, 57546, 40474, 47108, 57545, 57564, 40474,
         47108, 57563, 57543,     2]])


raw_sequence = processor.batch_decode(outputs.sequences)[0]
print(raw_sequence)

<s_cord-v2><s_menu><s_nm> POTATO SAUSAGE BREAD</s_nm><s_cnt> 1</s_cnt><s_price> 19,000</s_price><sep/><s_nm> OREO GREEN TEA SPREAD</s_nm><s_cnt> 1</s_cnt><s_price> 52,000</s_price><sep/><s_nm> WHITE CHOCO BANANA SPREAD</s_nm><s_cnt> 1</s_cnt><s_price> 52,000</s_price></s_menu><s_total><s_total_price> 123,000</s_total_price><s_creditcardprice> 123,000</s_creditcardprice></s_total></s>


sequence = raw_sequence.replace(processor.tokenizer.eos_token, "").replace(processor.tokenizer.pad_token, "") # remove </s> eos and <pad> token
sequence = re.sub(r"<.*?>", "", sequence, count=1).strip()  # remove <s_cord-v2> first task start token
sequence

'<s_menu><s_nm> POTATO SAUSAGE BREAD</s_nm><s_cnt> 1</s_cnt><s_price> 19,000</s_price><sep/><s_nm> OREO GREEN TEA SPREAD</s_nm><s_cnt> 1</s_cnt><s_price> 52,000</s_price><sep/><s_nm> WHITE CHOCO BANANA SPREAD</s_nm><s_cnt> 1</s_cnt><s_price> 52,000</s_price></s_menu><s_total><s_total_price> 123,000</s_total_price><s_creditcardprice> 123,000</s_creditcardprice></s_total>'


# code here: token to json
processor.token2json(sequence)

{'menu': [{'nm': 'POTATO SAUSAGE BREAD', 'cnt': '1', 'price': '19,000'},
  {'nm': 'OREO GREEN TEA SPREAD', 'cnt': '1', 'price': '52,000'},
  {'nm': 'WHITE CHOCO BANANA SPREAD', 'cnt': '1', 'price': '52,000'}],
 'total': {'total_price': '123,000', 'creditcardprice': '123,000'}}


# gambar yang di generate (images[6])
images[6]


def doc_to_text(input_img, task_prompt=task_prompt, model=model, processor=processor):
    # set model device
    device = "cuda" if torch.cuda.is_available() else "cpu"
    model.to(device)
    
    # document preprocessing
    pixel_values = processor(input_img, return_tensors="pt").pixel_values
    decoder_input_ids = processor.tokenizer(task_prompt, add_special_tokens=False, return_tensors="pt")["input_ids"]

    # sequence generation
    outputs = model.generate(
        pixel_values.to(device),
        decoder_input_ids=decoder_input_ids.to(device),
        max_length=model.decoder.config.max_position_embeddings,
        pad_token_id=processor.tokenizer.pad_token_id,
        eos_token_id=processor.tokenizer.eos_token_id,
        use_cache=True,
        bad_words_ids=[[processor.tokenizer.unk_token_id]],
        return_dict_in_generate=True,
        
        # modify parameters
        early_stopping=True,
        num_beams=2,
        output_scores=True,
    )
    
    # document post-processing: sequence token cleaning
    sequence = processor.batch_decode(outputs.sequences)[0]
    sequence = sequence.replace(processor.tokenizer.eos_token, "").replace(processor.tokenizer.pad_token, "")
    sequence = re.sub(r"<.*?>", "", sequence, count=1).strip()  # remove first task start token
    print(sequence)

    # output conversion: token to json
    output = processor.token2json(sequence)

    return output


# list untuk menyimpan hasil generate docs to text
preds = []

# code here: buatlah looping untuk predict 20 image dan disimpan di preds
# ...
for img in images[:20]:
    result=doc_to_text(img)
    preds.append(result)

<s_menu><s_nm> REAL GANACHE</s_nm><s_cnt> 1</s_cnt><s_price> 16,500</s_price><sep/><s_nm> EGG TART</s_nm><s_cnt> 1</s_cnt><s_price> 13,000</s_price><sep/><s_nm> PIZZA TOAST</s_nm><s_cnt> 1</s_cnt><s_price> 16,000</s_price></s_menu><s_total><s_total_price> 45,500</s_total_price><s_cashprice> 50,000</s_cashprice><s_changeprice> 4,500</s_changeprice></s_total>
<s_menu><s_nm> Kopi Susu Kolonel</s_nm><s_cnt> 1</s_cnt><s_price> 23.000</s_price></s_menu><s_total><s_total_price> 23.000</s_total_price><s_cashprice> 50.000</s_cashprice><s_changeprice> 27.000</s_changeprice></s_total>
<s_menu><s_nm> S-Ovaltine</s_nm><s_unitprice> 20,000</s_unitprice><s_cnt> 1</s_cnt><s_price> 20,000</s_price><s_sub><s_nm> 50%</s_nm></s_sub></s_menu><s_sub_total><s_subtotal_price> 18,181</s_subtotal_price><s_tax_price> 1,818</s_tax_price></s_sub_total><s_total><s_total_price> 20,000</s_total_price><s_cashprice> 100,000</s_cashprice><s_changeprice> 80,000</s_changeprice></s_total>
<s_menu><s_nm> M-Caramel Black Tea</s_nm><s_unitprice> @28,000</s_unitprice><s_cnt> 1X</s_cnt><s_price> 28,000</s_price><s_sub><s_nm> 70%</s_nm><sep/><s_nm> Less Ice</s_nm></s_sub></s_menu><s_sub_total><s_subtotal_price> 28,000</s_subtotal_price><s_tax_price> 0.</s_tax_price></s_sub_total><s_total><s_total_price> 28,000</s_total_price><s_cashprice> 28,000</s_cashprice><s_changeprice> 0</s_changeprice></s_total>
<s_menu><s_nm> BBQ Chicken</s_nm><s_cnt> 1</s_cnt><s_price> 41,000</s_price><s_sub><s_nm> Sedang</s_nm><s_cnt> 1</s_cnt><s_price> 0</s_price></s_sub></s_menu><s_sub_total><s_subtotal_price> 41,000</s_subtotal_price></s_sub_total><s_total><s_total_price> 41,000</s_total_price><s_cashprice> 50.000</s_cashprice><s_changeprice> 9,000</s_changeprice><s_menuqty_cnt> 1</s_menuqty_cnt></s_total>
<s_menu><s_nm> LE MINERAL</s_nm><s_price> 8,000</s_price></s_menu><s_sub_total><s_subtotal_price> 7,273</s_subtotal_price><s_tax_price> 727</s_tax_price></s_sub_total><s_total><s_total_price> 8,000</s_total_price><s_cashprice> 8,000</s_cashprice></s_total>
<s_menu><s_nm> POTATO SAUSAGE BREAD</s_nm><s_cnt> 1</s_cnt><s_price> 19,000</s_price><sep/><s_nm> OREO GREEN TEA SPREAD</s_nm><s_cnt> 1</s_cnt><s_price> 52,000</s_price><sep/><s_nm> WHITE CHOCO BANANA SPREAD</s_nm><s_cnt> 1</s_cnt><s_price> 52,000</s_price></s_menu><s_total><s_total_price> 123,000</s_total_price><s_creditcardprice> 123,000</s_creditcardprice></s_total>
<s_menu><s_nm> Choco Devil</s_nm><s_cnt> 4</s_cnt><s_price> 63,636</s_price><sep/><s_nm> CP 360 Club Card</s_nm><s_price> -9,545</s_price></s_menu><s_sub_total><s_subtotal_price> 63,636</s_subtotal_price><s_discount_price> -9,545</s_discount_price><s_tax_price> 5,409</s_tax_price></s_sub_total><s_total><s_total_price> 59,500</s_total_price><s_cashprice> 100,000</s_cashprice><s_changeprice> 40,500</s_changeprice></s_total>
<s_menu><s_nm> TALAM UNGU</s_nm><s_unitprice> @6500</s_unitprice><s_cnt> 3X</s_cnt><s_discountprice> -7,800</s_discountprice><s_price> 19,500</s_price><sep/><s_nm> MIKA KECIL</s_nm><s_unitprice> @0</s_unitprice><s_cnt> 1X</s_cnt><s_price> 0</s_price></s_menu><s_sub_total><s_subtotal_price> 11,700</s_subtotal_price></s_sub_total><s_total><s_total_price> 11,700</s_total_price><s_cashprice> 20,000</s_cashprice><s_changeprice> 8,300</s_changeprice><s_menuqty_cnt> 4.00xITEMs</s_menuqty_cnt></s_total>
<s_menu><s_nm> Tahu Ikan Oma Giok</s_nm><s_cnt> 1</s_cnt><s_price> 20.000</s_price></s_menu><s_total><s_total_price> 20.000</s_total_price><s_cashprice> 20.000</s_cashprice><s_changeprice> 0</s_changeprice></s_total>
<s_menu><s_nm> Serbu</s_nm><s_cnt> 2</s_cnt><s_price> 40.000</s_price><sep/><s_nm> Choco Peanut Bread</s_nm><s_cnt> 2</s_cnt><s_price> 20.000</s_price></s_menu><s_total><s_total_price> 60.000</s_total_price><s_cashprice> 60.000</s_cashprice><s_changeprice> 0</s_changeprice></s_total>
<s_menu><s_nm> Se'I Sapi Sambal Matah ( R )</s_nm><s_cnt> 1</s_cnt><s_price> 20.000</s_price><sep/><s_nm> Se'I S-pi Lada Hitam (J)</s_nm><s_cnt> 1</s_cnt><s_price> 35.000</s_price><sep/><s_nm> Nasi Putih</s_nm><s_cnt> 2</s_cnt><s_price> 10.000</s_price><sep/><s_nm> Milk Shake Coklat</s_nm><s_cnt> 1</s_cnt><s_price> 16.000</s_price></s_menu><s_sub_total><s_subtotal_price> 81.000</s_subtotal_price><s_tax_price> 8.100</s_tax_price></s_sub_total><s_total><s_total_price> 89.100</s_total_price><s_changeprice> 0</s_changeprice><s_creditcardprice> 89.100</s_creditcardprice></s_total>
<s_menu><s_nm> ES KOPI SUSU</s_nm><s_cnt> 4</s_cnt><s_price> 72.000</s_price></s_menu><s_total><s_total_price> 72.000</s_total_price><s_changeprice> 0</s_changeprice><s_emoneyprice> 72.000</s_emoneyprice></s_total>
<s_menu><s_nm> MINERAL 600 ML</s_nm><s_cnt> 1</s_cnt><s_price> 7,727</s_price><sep/><s_nm> BULGOGI RICE R</s_nm><s_cnt> 1</s_cnt><s_price> 33,636</s_price></s_menu><s_sub_total><s_subtotal_price> 41,364</s_subtotal_price><s_tax_price> 4,136</s_tax_price></s_sub_total><s_total><s_total_price> 45,500</s_total_price><s_cashprice> 50,000</s_cashprice><s_changeprice> -4,500</s_changeprice></s_total>
<s_menu><s_nm> Arem Arem</s_nm><s_unitprice> @12.000</s_unitprice><s_cnt> 2x</s_cnt><s_price> 24.000</s_price><sep/><s_nm> Kroket</s_nm><s_unitprice> @12.000</s_unitprice><s_cnt> 1x</s_cnt><s_price> 12.000</s_price></s_menu><s_sub_total><s_subtotal_price> Rp 36.000</s_subtotal_price><s_tax_price> Rp 3.600</s_tax_price></s_sub_total><s_total><s_total_price> Rp 39.600</s_total_price><s_emoneyprice> Rp 39.600</s_emoneyprice></s_total>
<s_menu><s_nm> Arem Arem</s_nm><s_unitprice> 12.000</s_unitprice><s_cnt> 2</s_cnt><s_price> 24.000</s_price><sep/><s_nm> Pepenero Pastel</s_nm><s_unitprice> 15.000</s_unitprice><s_cnt> 2</s_cnt><s_price> 30.000</s_price></s_menu><s_sub_total><s_subtotal_price> Rp 54.000</s_subtotal_price><s_tax_price> Rp 5.400</s_tax_price></s_sub_total><s_total><s_total_price> Rp 59.400</s_total_price><s_cashprice> Rp 100.000</s_cashprice><s_changeprice> Rp 40.600</s_changeprice></s_total>
<s_menu><s_nm> TT</s_nm><s_unitprice> 20,000</s_unitprice><s_cnt> 1</s_cnt><s_price> 20,000</s_price></s_menu><s_total><s_total_price> 20,000</s_total_price><s_cashprice> 100,000</s_cashprice><s_changeprice> 80,000</s_changeprice></s_total>
<s_menu><s_nm> LEMONADE 16OZ</s_nm><s_unitprice> 20,000</s_unitprice><s_cnt> 1 x</s_cnt><s_price> 20,000</s_price></s_menu><s_sub_total><s_subtotal_price> 20,000</s_subtotal_price></s_sub_total><s_total><s_total_price> 20,000</s_total_price><s_cashprice> 100,000</s_cashprice><s_changeprice> 80,000</s_changeprice></s_total>
<s_menu><s_nm> beef.c roll 3pcs</s_nm><s_unitprice> 10,000</s_unitprice><s_cnt> 1</s_cnt><s_price> 10,000</s_price><sep/><s_nm> kaya bred</s_nm><s_unitprice> 15,000</s_unitprice><s_cnt> 1</s_cnt><s_price> 15,000</s_price></s_menu><s_total><s_total_price> 25,000</s_total_price><s_cashprice> 100,000</s_cashprice><s_changeprice> 75,000</s_changeprice><s_menuqty_cnt> 2</s_menuqty_cnt></s_total>
<s_menu><s_nm> FUTAMI 17 GREEN TEA (CLASS</s_nm><s_cnt> 1</s_cnt><s_price> 12,500</s_price><sep/><s_nm> EGG TART</s_nm><s_cnt> 1</s_cnt><s_price> 13,000</s_price><sep/><s_nm> GRAIN CROQUE MONSIEUR</s_nm><s_cnt> 1</s_cnt><s_price> 17,000</s_price></s_menu><s_total><s_total_price> 42,500</s_total_price><s_cashprice> 50,000</s_cashprice><s_changeprice> 7,500</s_changeprice></s_total>


# code here: cek hasil prediksinya
preds[0]

{'menu': [{'nm': 'REAL GANACHE', 'cnt': '1', 'price': '16,500'},
  {'nm': 'EGG TART', 'cnt': '1', 'price': '13,000'},
  {'nm': 'PIZZA TOAST', 'cnt': '1', 'price': '16,000'}],
 'total': {'total_price': '45,500',
  'cashprice': '50,000',
  'changeprice': '4,500'}}


df_preds = pd.DataFrame.from_dict(preds)
df_preds


# code here
df_preds.isna().sum()

menu         0
total        0
sub_total    9
dtype: int64


df = pd.DataFrame(columns=['receipt_id', 'nm', 'cnt', 'price', 'total_price'])
df


# cara mengecek jumlah baris pada suatu dataframe
len(df)

0


for  index,row in df_preds.iterrows():
    print(index,row)

0 menu         [{'nm': 'REAL GANACHE', 'cnt': '1', 'price': '...
total        {'total_price': '45,500', 'cashprice': '50,000...
sub_total                                                  NaN
Name: 0, dtype: object
1 menu         {'nm': 'Kopi Susu Kolonel', 'cnt': '1', 'price...
total        {'total_price': '23.000', 'cashprice': '50.000...
sub_total                                                  NaN
Name: 1, dtype: object
2 menu         {'nm': 'S-Ovaltine', 'unitprice': '20,000', 'c...
total        {'total_price': '20,000', 'cashprice': '100,00...
sub_total    {'subtotal_price': '18,181', 'tax_price': '1,8...
Name: 2, dtype: object
3 menu         {'nm': 'M-Caramel Black Tea', 'unitprice': '@2...
total        {'total_price': '28,000', 'cashprice': '28,000...
sub_total      {'subtotal_price': '28,000', 'tax_price': '0.'}
Name: 3, dtype: object
4 menu         {'nm': 'BBQ Chicken', 'cnt': '1', 'price': '41...
total        {'total_price': '41,000', 'cashprice': '50.000...
sub_total                         {'subtotal_price': '41,000'}
Name: 4, dtype: object
5 menu                  {'nm': 'LE MINERAL', 'price': '8,000'}
total         {'total_price': '8,000', 'cashprice': '8,000'}
sub_total    {'subtotal_price': '7,273', 'tax_price': '727'}
Name: 5, dtype: object
6 menu         [{'nm': 'POTATO SAUSAGE BREAD', 'cnt': '1', 'p...
total        {'total_price': '123,000', 'creditcardprice': ...
sub_total                                                  NaN
Name: 6, dtype: object
7 menu         [{'nm': 'Choco Devil', 'cnt': '4', 'price': '6...
total        {'total_price': '59,500', 'cashprice': '100,00...
sub_total    {'subtotal_price': '63,636', 'discount_price':...
Name: 7, dtype: object
8 menu         [{'nm': 'TALAM UNGU', 'unitprice': '@6500', 'c...
total        {'total_price': '11,700', 'cashprice': '20,000...
sub_total                         {'subtotal_price': '11,700'}
Name: 8, dtype: object
9 menu         {'nm': 'Tahu Ikan Oma Giok', 'cnt': '1', 'pric...
total        {'total_price': '20.000', 'cashprice': '20.000...
sub_total                                                  NaN
Name: 9, dtype: object
10 menu         [{'nm': 'Serbu', 'cnt': '2', 'price': '40.000'...
total        {'total_price': '60.000', 'cashprice': '60.000...
sub_total                                                  NaN
Name: 10, dtype: object
11 menu         [{'nm': 'Se'I Sapi Sambal Matah ( R )', 'cnt':...
total        {'total_price': '89.100', 'changeprice': '0', ...
sub_total    {'subtotal_price': '81.000', 'tax_price': '8.1...
Name: 11, dtype: object
12 menu         {'nm': 'ES KOPI SUSU', 'cnt': '4', 'price': '7...
total        {'total_price': '72.000', 'changeprice': '0', ...
sub_total                                                  NaN
Name: 12, dtype: object
13 menu         [{'nm': 'MINERAL 600 ML', 'cnt': '1', 'price':...
total        {'total_price': '45,500', 'cashprice': '50,000...
sub_total    {'subtotal_price': '41,364', 'tax_price': '4,1...
Name: 13, dtype: object
14 menu         [{'nm': 'Arem Arem', 'unitprice': '@12.000', '...
total        {'total_price': 'Rp 39.600', 'emoneyprice': 'R...
sub_total    {'subtotal_price': 'Rp 36.000', 'tax_price': '...
Name: 14, dtype: object
15 menu         [{'nm': 'Arem Arem', 'unitprice': '12.000', 'c...
total        {'total_price': 'Rp 59.400', 'cashprice': 'Rp ...
sub_total    {'subtotal_price': 'Rp 54.000', 'tax_price': '...
Name: 15, dtype: object
16 menu         {'nm': 'TT', 'unitprice': '20,000', 'cnt': '1'...
total        {'total_price': '20,000', 'cashprice': '100,00...
sub_total                                                  NaN
Name: 16, dtype: object
17 menu         {'nm': 'LEMONADE 16OZ', 'unitprice': '20,000',...
total        {'total_price': '20,000', 'cashprice': '100,00...
sub_total                         {'subtotal_price': '20,000'}
Name: 17, dtype: object
18 menu         [{'nm': 'beef.c roll 3pcs', 'unitprice': '10,0...
total        {'total_price': '25,000', 'cashprice': '100,00...
sub_total                                                  NaN
Name: 18, dtype: object
19 menu         [{'nm': 'FUTAMI 17 GREEN TEA (CLASS', 'cnt': '...
total        {'total_price': '42,500', 'cashprice': '50,000...
sub_total                                                  NaN
Name: 19, dtype: object


# mengiterasi setiap rrow dalam df_preds
for index, row in df_preds.iterrows():

    # mengecek apakah field 'menu' adalah list, jika tidak, ubah menjadi list
    menus = row['menu'] if isinstance(row['menu'], list) else [row['menu']]

    # mengiterasi setiap elemen dalam list 'menus'
    for menu in menus:
        # menambahkan row baru ke 'df' dengan informasi dari 'menu' serta tambahan 'total_price' dan 'receipt_id'
        df.loc[len(df)] = {
            **menu,  # unpack semua pasangan key-value dari dictionary 'menu' yang cocok dg nama kolom yg ada
            'total_price': row['total']['total_price'],  # mengambil 'total_price' dari baris saat ini
            'receipt_id': img_filenames[index].split('.')[0]  # mengambil ID struk dari nama file gambar
        }

df


# menyimpan DataFrame 'df' ke dalam file csv
df.to_csv('receipt_extracted.csv', 
          index=False)  # berarti indeks DataFrame tidak disertakan dalam file csv


# cek tipe data
df.info()

<class 'pandas.core.frame.DataFrame'>
Index: 36 entries, 0 to 35
Data columns (total 5 columns):
 #   Column       Non-Null Count  Dtype 
---  ------       --------------  ----- 
 0   receipt_id   36 non-null     object
 1   nm           36 non-null     object
 2   cnt          34 non-null     object
 3   price        36 non-null     object
 4   total_price  36 non-null     object
dtypes: object(5)
memory usage: 1.7+ KB


new_columns_name = {
    'nm': 'item_name',
    'cnt': 'quantity'
}

df = df.rename(columns=new_columns_name)
df.head()


# fungsi untuk membersihkan string harga dari simbol dan spasi
def clean_price(x):
    return int(x.replace(".", "").replace(",", "").replace("Rp", "").replace(" ", ""))


# code here
clean_price(df.loc[0,"price"])

16500


# mengaplikasikan fungsi 'clean_price' ke setiap elemen di kolom 'price' pada 'df'
df['price'] = df['price'].apply(lambda x: clean_price(str(x)))


# code here: mengaplikasikan fungsi 'clean_price' ke setiap elemen di kolom 'total_price' pada 'df'
df['total_price'] = df['total_price'].apply(lambda x: clean_price(str(x)))
df.head()


df.info()

<class 'pandas.core.frame.DataFrame'>
Index: 36 entries, 0 to 35
Data columns (total 5 columns):
 #   Column       Non-Null Count  Dtype 
---  ------       --------------  ----- 
 0   receipt_id   36 non-null     object
 1   item_name    36 non-null     object
 2   quantity     34 non-null     object
 3   price        36 non-null     int64 
 4   total_price  36 non-null     int64 
dtypes: int64(2), object(3)
memory usage: 2.7+ KB


# membersihkan dan mengkonversi nilai 'x' menjadi float
def clean_quantity(x):
    # jika 'x' bernilai None (tidak ada data), kembalikan 0
    if x is None:
        return 0

    # mengonversi 'x' ke string, menghapus spasi, 'x'/'X', dan ']' dari string tersebut, dan mengembalikan menjadi sebuah angka
    return float(str(x).replace(" ", "").replace("x", "").replace("X", "").replace("]", ""))


# code here: mengaplikasikan fungsi 'clean_quantity' ke setiap elemen di kolom 'quantity' pada 'df'
df['quantity'] = df['quantity'].apply(lambda x: clean_quantity(str(x)))
df.head()

df


# code here
df_pivot = df.pivot_table(index=['receipt_id', 'total_price', 'item_name'])
df_pivot


import gradio as gr

gr.Interface(input=, output=, fn=, live=)


import gradio as gr

def my_function(name_text):
    return f"Hello, {name_text}. Nice to meet you!"

test = gr.Interface(fn=my_function, inputs="text", outputs="text", live=False, title="Hello World App")
test.launch(share=True)

Running on local URL:  http://127.0.0.1:7862
Running on public URL: https://665ebb33c4f2cca4d2.gradio.live

This share link expires in 72 hours. For free permanent hosting and GPU upgrades, run `gradio deploy` from Terminal to deploy to Spaces (https://huggingface.co/spaces)


model.eval()

# code here: let's create gradio
demo = gr.Interface(
    inputs="image",
    outputs="json",
    fn=doc_to_text,
    title="Real-time Receipt and Invoice Scanning"
)
demo.launch()

Running on local URL:  http://127.0.0.1:7864

To create a public link, set `share=True` in `launch()`.

<s_menu><s_nm> Quele No.3</s_nm><s_num> 09 Jan 2024</s_num><s_price> 13:37</s_price><sep/><s_nm> Receipt Number</s_nm><s_num> YQVSOC</s_num><s_price> QVSOC</s_price><sep/><s_nm> Customer</s_nm><s_num> Benjamin Theodor</s_nm><s_num> Order ID</s_nm><s_num> DTU0003</s_num><s_price> DTU0003</s_price><sep/><s_nm> Bill Name</s_nm><s_num> #An. Benjamin Collected By Dhavina Mutia</s_nm><s_num> *Dine In*</s_num><s_price> 13:37</s_price><sep/><s_nm> Anak Vaksinasi</s_nm><s_num> Anak</s_num><s_unitprice> @30.0000</s_unitprice><s_cnt> 1x</s_cnt><s_price> Theodor</s_price><sep/><s_nm> Konsultasi Dokter An</s_nm><s_num> Konsultasi ak B</s_nm><s_num> ISTLI</s_num><s_unitprice> @305.000</s_unitprice><s_cnt> 1x</s_cnt><s_price> 50.000</s_price><sep/><s_nm> JM Dokter Anak Vaksi nasi</s_nm><s_num> ISTLI</s_num><s_unitprice> @65.000</s_unitprice><s_cnt> 1x</s_cnt><s_price> 65.000</s_price><sep/><s_nm> Vaksin</s_nm><s_num> Prevenar Inj</s_nm><s_unitprice> @1.134.000</s_unitprice><s_cnt> 1x</s_cnt><s_price> 1,134.000</s_price><sep/><s_nm> Vaksin</s_nm><s_unitprice> @452.400</s_unitprice><s_cnt> 1x</s_cnt><s_price> 452.400</s_price><sep/><s_nm> Vaksin</s_nm><s_num> Rotategn</s_nm><s_unitprice> @544.050</s_unitprice><s_cnt> 1x</s_cnt><s_price> 544.050</s_price><sep/><s_nm> Needle 25</s_nm><s_unitprice> @3.500</s_unitprice><s_cnt> 1x</s_cnt><s_price> 3.500</s_price><sep/><s_nm> Tongue Spatula Depre</s_nm><s_num> ssor</s_nm><s_unitprice> @2.500</s_unitprice><s_cnt> 1x</s_cnt><s_price> 2.500</s_price><sep/><s_nm> Plester Anak</s_nm><s_unitprice> @ 1.000</s_unitprice><s_cnt> 2x</s_cnt><s_price> 2.000</s_price><sep/><s_nm> Swab Alkohol</s_nm><s_unitprice> @5.250</s_unitprice><s_cnt> 2x</s_cnt><s_price> 10.500</s_price></s_menu><s_sub_total><s_subtotal_price> Rp 2.568.950</s_subtotal_price><s_discount_price> (Rp 50)</s_discount_price></s_sub_total><s_total><s_total_price> Rp 2.588.900</s_total_price><s_emoneyprice> Rp 2.568.900</s_emoneyprice></s_total>


import re
import os
import torch

import gradio as gr
from PIL import Image
from transformers import DonutProcessor, VisionEncoderDecoderModel

processor = DonutProcessor.from_pretrained("naver-clova-ix/donut-base-finetuned-cord-v2")
model = VisionEncoderDecoderModel.from_pretrained("naver-clova-ix/donut-base-finetuned-cord-v2")

import pandas as pd
data_parquet = pd.read_parquet('data_input/test-00000-of-00001-9c204eb3f4e11791.parquet')
data_parquet.head()

import json
for index, row in df.iterrows():
    bytes = row['image']['bytes']
    labels = json.loads(row['ground_truth'])['gt_parse']

    with open(f'data_input/new/{index}.txt', 'w') as label_f:
        label_f.write(str(labels))
    with open(f'data_input/new/{index}.png', 'wb') as f:
        f.write(bytes)

Pandas dtype	Python type	Usage
object, str	str	Text or mixed numeric and non-numeric values
int64	int	Integer numbers
float64	float	Floating point numbers
bool	bool	True/False values
datetime64[ns]	-	Date and time values
timedelta[ns]	-	Differences between two datetimes
category	-	Finite list of text values

	receipt_id	item_name	count	price	total_price
0	ID0000	real ganache	1.0	16500	45500
1	ID0000	egg tart	1.0	13000	45500
2	ID0000	pizza toast	1.0	16000	45500
3	ID0001	kopi susu kolonel	1.0	23000	23000
4	ID0002	s-ovaltine	1.0	20000	20000
5	ID0003	m-carame 1 black tea	1.0	28000	28000
6	ID0004	bbq chicken	1.0	41000	41000
7	ID0005	le mineral	1.0	8000	8000
8	ID0006	potato sausage bread	1.0	19000	123000
9	ID0006	oreo green tea spread	1.0	52000	123000
10	ID0006	white choco banana spread	1.0	52000	123000
11	ID0007	choco devil	4.0	63636	59500
12	ID0007	cp 360 club card	1.0	-9545	59500
13	ID0008	talam ungu	3.0	19500	11700
14	ID0008	mika kecil	1.0	0	11700
15	ID0009	tahu ikan oma giok	1.0	20000	20000
16	ID0010	serbu	2.0	40000	60000
17	ID0010	choco peanut bread	2.0	20000	60000
18	ID0011	se'i sapi sambal matah ( r )	1.0	20000	89100
19	ID0011	se'i s-pi lada hitam (j)	1.0	35000	89100
20	ID0011	nasi putih	2.0	10000	89100
21	ID0011	milk shake coklat	1.0	16000	89100
22	ID0012	es kopi susu	4.0	72000	72000
23	ID0013	mineral 600 ml	1.0	7727	45500
24	ID0013	bulgogi rice r	1.0	33636	45500
25	ID0014	arem arem	2.0	24000	39600
26	ID0014	kroket	1.0	12000	39600
27	ID0015	arem arem	2.0	24000	59400
28	ID0015	pepenero pastel	2.0	30000	59400
29	ID0016	tt	1.0	20000	20000
30	ID0017	lemonade 16oz	1.0	20000	20000
31	ID0018	beef c roll 3pcs	1.0	10000	25000
32	ID0018	kaya bred	1.0	15000	25000
33	ID0019	futami 17 green tea (clas	1.0	12500	42500
34	ID0019	egg tart	1.0	13000	42500
35	ID0019	grain croque monsieur	1.0	17000	42500

	menu	total	sub_total
0	[{'nm': 'REAL GANACHE', 'cnt': '1', 'price': '...	{'total_price': '45,500', 'cashprice': '50,000...	NaN
1	{'nm': 'Kopi Susu Kolonel', 'cnt': '1', 'price...	{'total_price': '23.000', 'cashprice': '50.000...	NaN
2	{'nm': 'S-Ovaltine', 'unitprice': '20,000', 'c...	{'total_price': '20,000', 'cashprice': '100,00...	{'subtotal_price': '18,181', 'tax_price': '1,8...
3	{'nm': 'M-Caramel Black Tea', 'unitprice': '@2...	{'total_price': '28,000', 'cashprice': '28,000...	{'subtotal_price': '28,000', 'tax_price': '0.'}
4	{'nm': 'BBQ Chicken', 'cnt': '1', 'price': '41...	{'total_price': '41,000', 'cashprice': '50.000...	{'subtotal_price': '41,000'}
5	{'nm': 'LE MINERAL', 'price': '8,000'}	{'total_price': '8,000', 'cashprice': '8,000'}	{'subtotal_price': '7,273', 'tax_price': '727'}
6	[{'nm': 'POTATO SAUSAGE BREAD', 'cnt': '1', 'p...	{'total_price': '123,000', 'creditcardprice': ...	NaN
7	[{'nm': 'Choco Devil', 'cnt': '4', 'price': '6...	{'total_price': '59,500', 'cashprice': '100,00...	{'subtotal_price': '63,636', 'discount_price':...
8	[{'nm': 'TALAM UNGU', 'unitprice': '@6500', 'c...	{'total_price': '11,700', 'cashprice': '20,000...	{'subtotal_price': '11,700'}
9	{'nm': 'Tahu Ikan Oma Giok', 'cnt': '1', 'pric...	{'total_price': '20.000', 'cashprice': '20.000...	NaN
10	[{'nm': 'Serbu', 'cnt': '2', 'price': '40.000'...	{'total_price': '60.000', 'cashprice': '60.000...	NaN
11	[{'nm': 'Se'I Sapi Sambal Matah ( R )', 'cnt':...	{'total_price': '89.100', 'changeprice': '0', ...	{'subtotal_price': '81.000', 'tax_price': '8.1...
12	{'nm': 'ES KOPI SUSU', 'cnt': '4', 'price': '7...	{'total_price': '72.000', 'changeprice': '0', ...	NaN
13	[{'nm': 'MINERAL 600 ML', 'cnt': '1', 'price':...	{'total_price': '45,500', 'cashprice': '50,000...	{'subtotal_price': '41,364', 'tax_price': '4,1...
14	[{'nm': 'Arem Arem', 'unitprice': '@12.000', '...	{'total_price': 'Rp 39.600', 'emoneyprice': 'R...	{'subtotal_price': 'Rp 36.000', 'tax_price': '...
15	[{'nm': 'Arem Arem', 'unitprice': '12.000', 'c...	{'total_price': 'Rp 59.400', 'cashprice': 'Rp ...	{'subtotal_price': 'Rp 54.000', 'tax_price': '...
16	{'nm': 'TT', 'unitprice': '20,000', 'cnt': '1'...	{'total_price': '20,000', 'cashprice': '100,00...	NaN
17	{'nm': 'LEMONADE 16OZ', 'unitprice': '20,000',...	{'total_price': '20,000', 'cashprice': '100,00...	{'subtotal_price': '20,000'}
18	[{'nm': 'beef.c roll 3pcs', 'unitprice': '10,0...	{'total_price': '25,000', 'cashprice': '100,00...	NaN
19	[{'nm': 'FUTAMI 17 GREEN TEA (CLASS', 'cnt': '...	{'total_price': '42,500', 'cashprice': '50,000...	NaN

	receipt_id	nm	cnt	price	total_price
0	ID0000	REAL GANACHE	1	16,500	45,500
1	ID0000	EGG TART	1	13,000	45,500
2	ID0000	PIZZA TOAST	1	16,000	45,500
3	ID0001	Kopi Susu Kolonel	1	23.000	23.000
4	ID0002	S-Ovaltine	1	20,000	20,000
5	ID0003	M-Caramel Black Tea	1X	28,000	28,000
6	ID0004	BBQ Chicken	1	41,000	41,000
7	ID0005	LE MINERAL	NaN	8,000	8,000
8	ID0006	POTATO SAUSAGE BREAD	1	19,000	123,000
9	ID0006	OREO GREEN TEA SPREAD	1	52,000	123,000
10	ID0006	WHITE CHOCO BANANA SPREAD	1	52,000	123,000
11	ID0007	Choco Devil	4	63,636	59,500
12	ID0007	CP 360 Club Card	NaN	-9,545	59,500
13	ID0008	TALAM UNGU	3X	19,500	11,700
14	ID0008	MIKA KECIL	1X	0	11,700
15	ID0009	Tahu Ikan Oma Giok	1	20.000	20.000
16	ID0010	Serbu	2	40.000	60.000
17	ID0010	Choco Peanut Bread	2	20.000	60.000
18	ID0011	Se'I Sapi Sambal Matah ( R )	1	20.000	89.100
19	ID0011	Se'I S-pi Lada Hitam (J)	1	35.000	89.100
20	ID0011	Nasi Putih	2	10.000	89.100
21	ID0011	Milk Shake Coklat	1	16.000	89.100
22	ID0012	ES KOPI SUSU	4	72.000	72.000
23	ID0013	MINERAL 600 ML	1	7,727	45,500
24	ID0013	BULGOGI RICE R	1	33,636	45,500
25	ID0014	Arem Arem	2x	24.000	Rp 39.600
26	ID0014	Kroket	1x	12.000	Rp 39.600
27	ID0015	Arem Arem	2	24.000	Rp 59.400
28	ID0015	Pepenero Pastel	2	30.000	Rp 59.400
29	ID0016	TT	1	20,000	20,000
30	ID0017	LEMONADE 16OZ	1 x	20,000	20,000
31	ID0018	beef.c roll 3pcs	1	10,000	25,000
32	ID0018	kaya bred	1	15,000	25,000
33	ID0019	FUTAMI 17 GREEN TEA (CLASS	1	12,500	42,500
34	ID0019	EGG TART	1	13,000	42,500
35	ID0019	GRAIN CROQUE MONSIEUR	1	17,000	42,500

			price	quantity
receipt_id	total_price	item_name
ID0000	45500	EGG TART	13000.0	1.0
		PIZZA TOAST	16000.0	1.0
		REAL GANACHE	16500.0	1.0
ID0001	23000	Kopi Susu Kolonel	23000.0	1.0
ID0002	20000	S-Ovaltine	20000.0	1.0
ID0003	28000	M-Caramel Black Tea	28000.0	1.0
ID0004	41000	BBQ Chicken	41000.0	1.0
ID0005	8000	LE MINERAL	8000.0	NaN
ID0006	123000	OREO GREEN TEA SPREAD	52000.0	1.0
		POTATO SAUSAGE BREAD	19000.0	1.0
		WHITE CHOCO BANANA SPREAD	52000.0	1.0
ID0007	59500	CP 360 Club Card	-9545.0	NaN
ID0007	59500	Choco Devil	63636.0	4.0
ID0008	11700	MIKA KECIL	0.0	1.0
ID0008	11700	TALAM UNGU	19500.0	3.0
ID0009	20000	Tahu Ikan Oma Giok	20000.0	1.0
ID0010	60000	Choco Peanut Bread	20000.0	2.0
ID0010	60000	Serbu	40000.0	2.0
ID0011	89100	Milk Shake Coklat	16000.0	1.0
		Nasi Putih	10000.0	2.0
		Se'I S-pi Lada Hitam (J)	35000.0	1.0
		Se'I Sapi Sambal Matah ( R )	20000.0	1.0
ID0012	72000	ES KOPI SUSU	72000.0	4.0
ID0013	45500	BULGOGI RICE R	33636.0	1.0
ID0013	45500	MINERAL 600 ML	7727.0	1.0
ID0014	39600	Arem Arem	24000.0	2.0
ID0014	39600	Kroket	12000.0	1.0
ID0015	59400	Arem Arem	24000.0	2.0
ID0015	59400	Pepenero Pastel	30000.0	2.0
ID0016	20000	TT	20000.0	1.0
ID0017	20000	LEMONADE 16OZ	20000.0	1.0
ID0018	25000	beef.c roll 3pcs	10000.0	1.0
ID0018	25000	kaya bred	15000.0	1.0
ID0019	42500	EGG TART	13000.0	1.0
		FUTAMI 17 GREEN TEA (CLASS	12500.0	1.0
		GRAIN CROQUE MONSIEUR	17000.0	1.0

DSS: Streamlining Invoice Processing¶

Document Understanding Transformer for Efficient Business Operations in Python¶

Background¶

Output¶

🎯 Training Objectives¶

Python Programming Basics¶

Anaconda Environment Preparation¶

Cara Membuat Environtment Baru:¶

Install/Update Package¶

🧪 Knowledge Check¶

Working with Jupyter Notebook (.ipynb)¶

Markdown Cell dan Code Cell¶

Command Mode and Edit Mode¶

Understanding Fundamental of Variables & Python Data Types¶

Variables¶

Python Data Types¶

(1) 🔠 String¶

(2) 🔢 Number¶

(3) ✅ Boolean¶

(4) 🗃️ List¶

(5) 🧾Dictionary¶

📌 Highlight Poin: Tipe Data di Python¶

Exploring Python If-Else Statements, Functions, ang Looping Concepts¶

If-Else Statements¶

Function¶

Looping (Perulangan)¶

Working with Dataframe pandas¶

Understanding Dataframe pandas¶

Read Data¶

pandas Data Types¶

Additional: Object & Categorical Variables¶

Master Data Manipulation & Pre-processing¶

Dive Deeper into String Data Types¶

Contingency Tables / Frequency Tables¶

Perform Conditional Subsetting Operations¶

Document Understanding Transformer (DUT) Utilization¶

Introduction to 🍩 Donut Model¶

What is 🍩 Donut Model?¶

Why Use 🍩 Donut Model?¶

How to Use 🍩 Donut Model for Document Information Extraction?¶

Document Information Extraction Using Donut¶

1️⃣ Read Document Images¶

2️⃣ Document Pre-processing¶

3️⃣ Sequence Generation¶

4️⃣ Document Post-Processing: Sequence Token Cleaning¶

5️⃣ Output Conversion: Token to JSON¶

🍩 All-in-One Function to Generate Document Information¶

Data Analysis Enhancement with Donut Outputs¶

Transform Donut Outputs to Dataframe pandas¶

💭 Discussion¶

Data Wrangling¶

Data Cleaning¶

🤿 (Opsional) Dive Deeper: 🍩 Advanced Document Extracted Dataframe¶

Integration Gradio for Efficient Scanning¶

Understand the Fundamentals of Gradio¶

Main Concept:¶

Additional gr.Interface Parameters:¶

Simple Examples of Usage¶

Develop Gradio for Real-time Receipt and Invoice Scanning¶

Reference¶

[Additional]¶

🌐 How to Deploy the Gradio¶

🍩 How to Fine Tuning Model Donut¶

🛠️ Tools Verification¶

🗃️ How to Read .parquet Data?¶

Working with Dataframe `pandas`¶

Understanding Dataframe `pandas`¶

`pandas` Data Types¶

Transform Donut Outputs to Dataframe `pandas`¶

Additional `gr.Interface` Parameters:¶

🗃️ How to Read `.parquet` Data?¶